Article Users Activity Gesture Recognition on Kinect Sensor Using Convolutional Neural Networks and FastDTW for Controlling Movements of a Mobile Robot

Abstract

In this paper, we use data from the Microsoft Kinect sensor that processes the captured image of a person using and extracting the joints information on every frame. Then, we propose the creation of an image derived from all the sequential frames of a gesture the movement, which facilitates training in a convolutional neural network. We trained a CNN using two strategies: combined training and individual training. The strategies were experimented in the convolutional neural network (CNN) using the MSRC-12 dataset, obtaining an accuracy rate of 86.67% in combined training and 90.78% of accuracy rate in the individual training. Then, the trained neural network was used to classify data obtained from Kinect with a person, obtaining an accuracy rate of 72.08% in combined training and 81.25% in individualized training. Finally, we use the system to send commands to a mobile robot in order to control it.

FastDTW is Approximate and Generally Slower Than the Algorithm it Approximates

“…These histograms show that majority of time series subsequences considered are less than 1,000 datapoints, and more importantly, the best value for w is rarely above 10%. Almost all uses of FastDTW fall into Case A [7], [8], [9], [10], [11], [12], [13], [14], [15], [16], [17], [18], and in every case the researchers using FastDTW would have been better off using classic cDTW, which would have been much faster, and exact.…”

“…Case D is the case emphasized by the original authors of the FastDTW paper as the best case for their algorithms. However, they did not show any real-world examples of such datasets, and a (admittedly incomplete) survey of the papers that refence FastDTW does not show any examples in the literature [7], [8], [9], [10], [11], [12], [13], [14], [15], [16], [17], [18].…”

“…• "the distances between the time series are computed using FastDTW" [13]. To gauge how commonly used this algorithm is, consider the fact that at least five papers use the term FastDTW in their title [14], [15], [16], [17], [18].…”

Weakly-Supervised Image Semantic Segmentation Based on Superpixel Region Merging

“…Our constraint is to transfer the superpixel tag to a zone tag. Three conditions should be met: (1) The image contains at least one super pixel label, (2) There can only be one label in a region, (3) The label of the area should be a super pixel set having the same label. Our goal is to superimpose the merged area as a superimposed model in such a way that the FCN's network training becomes the superpixel regression problem of the ground-based segmentation model [15].…”

“…In the last few years, convolutional neural networks [1][2][3][4] (CNN) have had widespread applications in various industries. The state-of-the-art semantic segmentation methods [5][6][7][8][9] rely on convolutional neural networks.…”